Computer Science ›› 2019, Vol. 46 ›› Issue (10): 19-26.doi: 10.11896/jsjkx.191000531C

• Big Data & Data Science • Previous Articles     Next Articles

Sentiment Analysis of User Comments Based on Extraction of Key Words and Key Sentences

YU Ying1, CHEN Ke1,2, SHOU Li-dan1,2, CHEN Gang1,2, WU Xiao-fan3   

  1. (College of Computer Science and Technology,Zhejiang University,Hangzhou 310027,China)1
    (Key Laboratory of Big Data Intelligent Computing of Zhejiang Province (Zhejiang University),Hangzhou 310027,China)2
    (Netease (Hangzhou) Network Co.,Ltd,Hangzhou 310051,China)3
  • Received:2018-07-11 Revised:2018-09-15 Online:2019-10-15 Published:2019-10-21

Abstract: One of the main task of sentiment analysis is to determine the polarity of a review whether it is positive or negative according to the content of the document.When determining the emotional polarity of a document,different sentences and words have different emotional contribution on the classification result,so how to extract more related words and sentences becomes an important problem.In the experiment of the supervised classification,this paper used the dependency syntactic analysis to extract the words which are more related to the emotion and can improve the classification effect.In the semi-supervised classification experiment,the key sentence extraction and the combining-classifier method based on the Chinese comments have been used.For key sentence extraction,the proposed approach takes the following attributes into account:sentiment attribute,position attribute,special word attribute and punctuation attri-bute.This approach extracts key sentences containing more emotional words and summary meaning,then uses combining-classifier method to make the sub classifier with the highest confidence to determine the classification effect.The results show that the performance of the proposed method is better than the baseline methods,which proves the validity of keyword extraction based on the dependency parsing and key Chinese sentence extraction algorithms.

Key words: Co-training method, Dependency parsing, Key sentence extraction, Semi-supervised learning, Sentiment analysis

CLC Number: 

  • TP391
[1]TURNEY P D.Thumbs up or thumbs down?:semantic orienta-tion applied to unsupervised classification of reviews[C]//Proceedings of the 40th Annual Meeting on Association for Computational Linguistics.Association for Computational Linguistics,2002:417-424.
[2]NAKAGAWA T,INUI K,KUROHASHI S.Dependency tree-based sentiment classification using CRFs with hidden variables[C]//Human Language Technologies:Conference of the North American Chapter of the Association of Computational Linguistics.Los Angeles,California,USA,DBLP,2010:786-794.
[3]MCDONALD R T,HANNAN K,NEYLON T,et al.Structured Models for Fine-to-Coarse Sentiment Analysis[C]//Proceedings of the,Meeting of the Association for Computational Linguistics(ACL 2007).Prague,Czech Republic,DBLP,2007:30-32.
[4]ABBASI A,FRANCE S,ZHANG Z,et al.Selecting Attributes for Sentiment Classification Using Feature Relation Networks[J].IEEE Transactions on Knowledge & Data Engineering,2011,23(3):447-462.
[5]AGARWAL A,XIE B,VOVSHA I,et al.Sentiment analysis of twitter data[C]//Proceedings of the Workshop on Language in Social Media (LSM 2011).2011:30-38.
[6]LIU J W,LIU Y,LUO X Q.Semi-supervised learning method[J].Journal of Computer Science,2015(8):1592-1617.
[7]MIKOLOV T,CHEN K,CORRADO G,et al.Efficient estimation of word representations in vector space[J].arXiv:1301.3781.
[8]LE Q,MIKOLOV T.Distributed representations of sentences and documents[C]//International Conference on Machine Learning.2014:1188-1196.
[9]ZHOU X,WAN X,XIAO J.Cross-lingual sentiment classification with bilingual document representation learning[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.2016:1403-1412.
[10]BOJANOWSKI P,GRAVE E,JOULIN A,et al.Enriching word vectors with subword information[J].arXiv:1607.04606.
[11]PETERS M E,NEUMANN M,IYYER M,et al.Deep contextualized word representations[J].arXiv:1802.05365.
[12]DEVLIN J,CHANG M W,LEE K,et al.BERT:Pre-training of Deep Bidirectional Transformers for Language Understanding[J].arXiv:1810.04805.
[13]TAN S,WANG Y,CHENG X.Combining learn-based and lexicon-based techniques for sentiment detection without using labeled examples[C]//Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.ACM,2008:743-744.
[14]CAMBRIA E,PORIA S,HAZARIKA D,et al.SenticNet 5:Discovering conceptual primitives for sentiment analysis by means of context embeddings[C]//Thirty-Second AAAI Conference on Artificial Intelligence.2018.
[15]SCUDDER H J.Probability of error of some adaptive pattern-recognition machines[J].IEEE Transactions on Information Theory,1965,11(3):363-371.
[16]FRALICK S C.Learning to recognize patterns without a teacher[J].IEEE Transactions on Information Theory,1967,13(1):57-64.
[17]AGRAWALA A K.Learning with a probabilistic teacher[J].IEEE Transactions on Information Theory,1970,16(4):373-379.
[18]PARK S B,ZHANG B T.Co-trained support vector machines for large scale unstructured document classification using unlabeled data and syntactic information[J].Information Processing &Management,2004,40(3):421-439.
[19]KIRITCHENKO S,MATWIN S.Email classification with co-training[C]//Proceedings of the 2011 Conference of the Center for Advanced Studies on Collaborative Research.IBM Corp,2011:301-312.
[20]SU Y,JU S,WANG Z,et al.Semi-supervised sentiment classification with random feature subspace method [J].Journal of Chinese Information Processing,2012,26(4):85-91.
[1] WU Hong-xin, HAN Meng, CHEN Zhi-qiang, ZHANG Xi-long, LI Mu-hang. Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning [J]. Computer Science, 2022, 49(8): 12-25.
[2] HOU Xia-ye, CHEN Hai-yan, ZHANG Bing, YUAN Li-gang, JIA Yi-zhen. Active Metric Learning Based on Support Vector Machines [J]. Computer Science, 2022, 49(6A): 113-118.
[3] WANG Yu-fei, CHEN Wen. Tri-training Algorithm Based on DECORATE Ensemble Learning and Credibility Assessment [J]. Computer Science, 2022, 49(6): 127-133.
[4] XU Hua-jie, CHEN Yu, YANG Yang, QIN Yuan-zhuo. Semi-supervised Learning Method Based on Automated Mixed Sample Data Augmentation Techniques [J]. Computer Science, 2022, 49(3): 288-293.
[5] DING Feng, SUN Xiao. Negative-emotion Opinion Target Extraction Based on Attention and BiLSTM-CRF [J]. Computer Science, 2022, 49(2): 223-230.
[6] XIAN Yan-tuan, GAO Fan-ya, XIANG Yan, YU Zheng-tao, WANG Jian. Improving Low-resource Dependency Parsing Using Multi-strategy Data Augmentation [J]. Computer Science, 2022, 49(1): 73-79.
[7] YUAN Jing-ling, DING Yuan-yuan, SHENG De-ming, LI Lin. Image-Text Sentiment Analysis Model Based on Visual Aspect Attention [J]. Computer Science, 2022, 49(1): 219-224.
[8] HU Yan-li, TONG Tan-qian, ZHANG Xiao-yu, PENG Juan. Self-attention-based BGRU and CNN for Sentiment Analysis [J]. Computer Science, 2022, 49(1): 252-258.
[9] DAI Hong-liang, ZHONG Guo-jin, YOU Zhi-ming , DAI Hong-ming. Public Opinion Sentiment Big Data Analysis Ensemble Method Based on Spark [J]. Computer Science, 2021, 48(9): 118-124.
[10] ZHANG Jin, DUAN Li-guo, LI Ai-ping, HAO Xiao-yan. Fine-grained Sentiment Analysis Based on Combination of Attention and Gated Mechanism [J]. Computer Science, 2021, 48(8): 226-233.
[11] SHI Wei, FU Yue. Microblog Short Text Mining Considering Context:A Method of Sentiment Analysis [J]. Computer Science, 2021, 48(6A): 158-164.
[12] PAN Fang, ZHANG Hui-bing, DONG Jun-chao, SHOU Zhao-yu. Aspect Sentiment Analysis of Chinese Online Course Review Based on Efficient Transformer [J]. Computer Science, 2021, 48(6A): 264-269.
[13] LI Jian-lan, PAN Yue, LI Xiao-cong, LIU Zi-wei, WANG Tian-yu. Chinese Commentary Text Research Status and Trend Analysis Based on CiteSpace [J]. Computer Science, 2021, 48(11A): 17-21.
[14] XU Lin-hong, LIU Xin, YUAN Wei, QI Rui-hua. Construction and Application of Russian Multimodal Emotion Corpus [J]. Computer Science, 2021, 48(11): 312-318.
[15] ZHANG Yan, LI Tian-rui. Review of Comment-oriented Aspect-based Sentiment Analysis [J]. Computer Science, 2020, 47(6): 194-200.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!